A novel video recommendation system based on efficient retrieval of human actions
详细信息 查看全文
- 作者：Mohsen Ramezani ramezani@semnan.ac.ir" class="auth_mail" title="E-mail the corresponding author ; Farzin Yaghmaee ; f_yaghmaee@semnan.ac.ir" class="auth_mail" title="E-mail the corresponding author
- 关键词：Recommender systems ; Content based retrieval ; Human actions ; Action representation ; Fuzzy dissimilarity measure
- 刊名：Physica A: Statistical Mechanics and its Applications
- 出版年：2016
- 出版时间：1 September 2016
- 年：2016
- 卷：457
- 期：Complete
- 页码：607-623
- 全文大小：3438 K
文摘
- •
Recommender Systems face some important challenges like sparse cold start user.
- •
Advancement of computer vision techniques can help solving such challenges.
- •
A query video and the content models can be used for recommending to cold starts.
- •
Due to relating most videos to humans, they are modeled based on included action.
- •
A low complex and more scalable method is presented to find recommended videos.